ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment

Automatically find issues in image datasets and practice data-centric computer vision.

Understand Human Behavior to Align True Needs

Japanese input method for fcitx5, powered by azooKey engine

This repo contains the code for our paper An Image is Worth 32 Tokens for Reconstruction and Generation

🚪✊Knock Knock: Get notified when your training ends with only two additional lines of code

STAIR captions: large-scale Japanese image caption dataset

PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.

A simple but robust PyTorch implementation of RetNet from "Retentive Network: A Successor to Transformer for Large Language Models" (https://arxiv.org/pdf/2307.08621.pdf)

Implementation of MagViT2 Tokenizer in Pytorch

a research paper for generative cartoon interpolation

Minimal implementation of scalable rectified flow transformers, based on SD3's approach

DiffSeg is an unsupervised zero-shot segmentation method using attention information from a stable-diffusion model. This repo implements the main DiffSeg algorithm and additionally includes an expe…

CeTZ: ein Typst Zeichenpaket - A library for drawing stuff with Typst.

A Native-PyTorch Library for LLM Fine-tuning

High-quality PNGs for logos I made for fun

Open-source and strong foundation image recognition models.

Kana-Kanji Conversion Module written in Swift

A pytorch quantization backend for optimum

Apply screentone to line drawings or colored illustrations with diffusion models.

[WIP] Layer Diffusion for WebUI (via Forge)

Transparent Image Layer Diffusion using Latent Transparency

🕵️‍♂️ All-in-one OSINT tool for analysing any website

A data-driven line extractor for 2D anime, manga and illustration using Keras.

Repo for my Tensorflow/Keras CV experiments. Mostly revolving around the Danbooru20xx dataset

A list of useful payloads and bypass for Web Application Security and Pentest/CTF

a family of highly capabale yet efficient large multimodal models